Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text generation model training method and device and text generation method and device

A technology for generating models and training methods, applied in the field of deep learning, which can solve the problems of lack of correlation and consistency, and low quality of lyrics

Pending Publication Date: 2020-10-16
NETEASE (HANGZHOU) NETWORK CO LTD
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the lyric generation model in the prior art is to iteratively generate the entire lyric by outputting a single lyric. This way of outputting a single lyric makes the quality of the generated lyric low, and there is a lack of correlation and Consistency, which further leads to low quality of generated lyrics

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Text generation model training method and device and text generation method and device
  • Text generation model training method and device and text generation method and device
  • Text generation model training method and device and text generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the appended The figures are only for the purpose of illustration and description, and are not used to limit the protection scope of the present application. Additionally, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented in accordance with some embodiments of the application. It should be understood that the operations of the flowcharts may be performed out of order, and steps that have no logical context may be performed in reverse order or concurrently. In addition, those skilled in the art may add one or more other operations t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a text generation model training method and device and a text generation method and device, and the method comprises the steps: obtaining first training data which comprises multi-dimensional sample control information and a first sample text, wherein the first sample text comprises a plurality of simple sentence texts; and taking the sample control information as input of atext generation model, obtaining an output result of the text generation model based on the first parameter and the sample control information, and adjusting the first parameter according to the output result and the first sample text until the output result of the text generation model is consistent with the first sample text to obtain a text generation model comprising a trained second parameter. According to the text generation method and device, the trained text generation model can output the target text including the complete target text (namely, the target text including multiple single sentence texts) based on the input multi-dimensional target control information, the correlation and fluency between the long texts are guaranteed, and the text quality of the generated target textis improved.

Description

technical field [0001] The present application relates to the technical field of deep learning, in particular, to a text generation model training method and device, and a text generation method and device. Background technique [0002] With the rapid development of deep learning technology and computer computing power, breakthroughs have been made in various research directions of natural language processing, such as machine translation and text generation (such as generating lyrics). [0003] In the field of text generation, based on the lyrics generation model trained in the existing way, the input of the lyrics generation model is the lyrics type, and the output is the single sentence lyrics. After the single sentence lyrics are generated, the next single sentence lyrics is generated again based on the generated single sentence lyrics. This back and forth, finally get the whole song lyrics. [0004] However, the lyric generation model in the prior art is to iteratively ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F40/289G06F40/30G06N3/04
CPCG06F40/289G06F40/30G06N3/044G06N3/045
Inventor 张荣升毛晓曦李乐范长杰胡志鹏
Owner NETEASE (HANGZHOU) NETWORK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products